Fault Diagnosis of Airborne Equipments Based on Similarity Search

The flight data generated during airplane's flights can be used for fault diagnosis, which is of great importance for improving the security and reducing the cost of maintenance of airplanes. It's an important fault diagnosis method t ofind out novel patterns of flight data, but flight data has characteristics of high dimension and containing stochastic noise. In this paper, we take advantage of similarity querying method t ofind out novel patterns in order to reduce the negative effect brought by high dimension and stochastic noise. Firstly, we reduce the dimension and eliminate the stochastic noise of flight data by piecewise linear representation method. Then, the indexical tree based on distance reduction rate is created to achieve efficient search. At last, the proposed approach is evaluated with a series of experiments on simulative data and real-world data. The experimental results show that this method can be successfully applied in practice.